---
title: gemma-2-9b-it-SimPO
canonical_url: "https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO"
md_url: "https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO.md"
repository: mlx-community/gemma-2-9b-it-SimPO
last_updated: 2024-12-19
license: mit
model_type:
  - gemma2
architectures:
  - Gemma2ForCausalLM
base_model:
  - google/gemma-2-9b-it
base_model_relation: finetune
parameters: 9.2B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1006
stars: 0
tags:
  - alignment-handbook
  - generated_from_trainer
  - mlx
---

# gemma-2-9b-it-SimPO

> gemma-2-9b-it-SimPO - mlx-community 在 ModelScope 开源的模型。mlx-community/gemma-2-9b-it-SimPO

mlx-community/gemma-2-9b-it-SimPO 是 ModelScope 魔搭社区上的 9.2B 参数机器学习模型，采用 mit 许可，基于 google/gemma-2-9b-it 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/gemma-2-9b-it-SimPO
- **License**: mit
- **Parameters**: 9.2B
- **Base model**: google/gemma-2-9b-it
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: alignment-handbook, generated_from_trainer, mlx
- **Downloads**: 1006
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO

---

# mlx-community/gemma-2-9b-it-SimPO

The Model [mlx-community/gemma-2-9b-it-SimPO](https://huggingface.co/mlx-community/gemma-2-9b-it-SimPO) was converted to MLX format from [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) using mlx-lm version **0.18.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-9b-it-SimPO")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```